© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 12390
    Prev
    Next
    INDEX
    Explanations

    concepts related to legacy and remembrance

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    цездатний
    -0.68
    oa̍t
    -0.61
    łecz
    -0.60
    */),
    -0.59
     bicara
    -0.56
    AutoresizingMask
    -0.56
     stable
    -0.55
    Leary
    -0.55
     geval
    -0.54
    uxxxx
    -0.53
    POSITIVE LOGITS
     unforgettable
    0.72
     memorable
    0.71
     memories
    0.70
     indelible
    0.68
     memory
    0.66
     forever
    0.65
     FOREVER
    0.63
     Forever
    0.61
     legacies
    0.61
     remembrance
    0.59
    Activations Density 0.113%

    No Known Activations